U.S. patent application number 15/818747 was filed with the patent office on 2018-06-07 for proposal candidate presentation device and proposal candidate presentation method.
The applicant listed for this patent is Panasonic Intellectual Property Management Co., Ltd.. Invention is credited to YUICHI AOKI, AKIRA ASAI, YASUKO IKETSUKI, MOTOJI OHMORI, ATSUSHI SASO.
Application Number | 20180158155 15/818747 |
Document ID | / |
Family ID | 62243331 |
Filed Date | 2018-06-07 |
United States Patent
Application |
20180158155 |
Kind Code |
A1 |
IKETSUKI; YASUKO ; et
al. |
June 7, 2018 |
PROPOSAL CANDIDATE PRESENTATION DEVICE AND PROPOSAL CANDIDATE
PRESENTATION METHOD
Abstract
A proposal candidate presentation device that includes: a
biological reaction information generator that generates biological
reaction information; a dialogue content information generator that
generates dialogue content information including dialogue content
between the customer and a proposer; a determiner that determines
whether a customer reaction to a question from the proposer is
positive or negative, based on the biological reaction information
and dialogue content information; a proposal candidate generator
that generates a customer proposal candidate information, based on
a customer response to the question, when it is determined that the
customer reaction based on the biological reaction information is
positive and the customer reaction based on the dialogue content
information is positive; and a re-question generator that generates
first re-question information having the same perspective as the
question, when the customer reaction based on the biological
reaction information and the customer reaction based on the
dialogue content information do not match.
Inventors: |
IKETSUKI; YASUKO; (Tokyo,
JP) ; SASO; ATSUSHI; (Kanagawa, JP) ; AOKI;
YUICHI; (Osaka, JP) ; ASAI; AKIRA; (Osaka,
JP) ; OHMORI; MOTOJI; (Osaka, JP) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
Panasonic Intellectual Property Management Co., Ltd. |
Osaka |
|
JP |
|
|
Family ID: |
62243331 |
Appl. No.: |
15/818747 |
Filed: |
November 21, 2017 |
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G10L 15/22 20130101;
G06N 5/02 20130101; G10L 15/1815 20130101; G06Q 50/14 20130101;
G06Q 30/0631 20130101; G10L 15/26 20130101; G06N 5/04 20130101 |
International
Class: |
G06Q 50/14 20060101
G06Q050/14; G06Q 30/06 20060101 G06Q030/06; G10L 15/26 20060101
G10L015/26; G10L 15/18 20060101 G10L015/18; G10L 15/22 20060101
G10L015/22 |
Foreign Application Data
Date |
Code |
Application Number |
Dec 6, 2016 |
JP |
2016-237087 |
Claims
1. A proposal candidate presentation device, comprising: a
biological reaction information generator that acquires biological
data of a customer, and generates biological reaction information
including the biological data and first time information indicating
a time at which the biological data was acquired; a dialogue
content information generator that acquires dialogue content
between the customer and a proposer, and generates dialogue content
information including dialogue information indicating the dialogue
content and second time information indicating a time at which the
dialogue content was acquired; a countermeasure determiner that
determines whether a reaction of the customer regarding a question
asked by the proposer is a positive reaction or a negative
reaction, based on the biological reaction information, and
determines whether the reaction of the customer regarding the
question is a positive reaction or a negative reaction, based on
the dialogue content information; a proposal candidate generator
that generates proposal candidate information indicating at least
one proposal for the customer, based on a response of the customer
regarding the question, in a case where it is determined that a
reaction of the customer based on the biological reaction
information is a positive reaction and a reaction of the customer
based on the dialogue content information is a positive reaction;
and a re-question generator that generates first re-question
information indicating first re-question having a same perspective
as a perspective of the question, in a case where the reaction of
the customer based on the biological reaction information and the
reaction of the customer based on the dialogue content information
do not match.
2. The proposal candidate presentation device according to claim 1,
further comprising: a proposal candidate storer that stores the
proposal candidate information, which is set in advance with
respect to the question, wherein the proposal candidate generator
extracts the proposal candidate information that has been set with
respect to the question, from the proposal candidate storer, in a
case where it is determined that the reaction of the customer based
on the biological reaction information is a positive reaction and
the reaction of the customer based on the dialogue content
information is a positive reaction.
3. The proposal candidate presentation device according to claim 1,
further comprising: a question storer that stores, in association
with each other, question information indicating each of a
plurality of questions including the question, and attribute
information indicating a perspective of each of the plurality of
questions, wherein the re-question generator extracts the question
information associated with the attribute information indicating a
same perspective as the perspective of the question, from the
stored question information as the first re-question information,
in a case where the reaction of the customer based on the
biological reaction information and the reaction of the customer
based on the dialogue content information do not match.
4. The proposal candidate presentation device according to claim 3,
wherein a degree of similarity indicating a mutual similarity is
set between the respective perspectives of the attribute
information, and the re-question generator decides the attribute
information having the degree of similarity that is equal to or
greater than a predetermined value with respect to the perspective
of the question, as the attribute information indicating the same
perspective as the perspective of the question.
5. The proposal candidate presentation device according to claim 1,
wherein the re-question generator generates second re-question
information indicating second re-question having a different
perspective from the perspective of the question included in the
dialogue content, when a case where the reaction of the customer
based on the biological reaction information and the reaction of
the customer based on the dialogue content information do not match
has been repeated a predetermined number of times with respect to
the first re-question indicated by the first re-question
information.
6. The proposal candidate presentation device according to claim 5,
further comprising: a question storer that stores, in association
with each other, question information indicating each of a
plurality of questions including the question, and attribute
information indicating a perspective of each of the plurality of
questions, wherein the re-question generator extracts the question
information associated with the attribute information indicating a
different perspective from the perspective of the question, from
the stored question information as the second re-question
information, when a case where the reaction of the customer based
on the biological reaction information and the reaction of the
customer based on the dialogue content information do not match has
been repeated a predetermined number of times with respect to the
first re-question indicated by the first re-question
information.
7. The proposal candidate presentation device according to claim 1,
wherein the re-question generator generates second re-question
information indicating second re-question having a different
perspective from the perspective of the question, in a case where
the reaction of the customer based on the biological reaction
information is a negative reaction and the reaction of the customer
based on the dialogue content information is a negative
reaction.
8. The proposal candidate presentation device according to claim 7,
further comprising: a question storer that stores, in association
with each other, question information indicating each of a
plurality of questions including the question, and attribute
information indicating a perspective of each of the plurality of
questions, wherein the re-question generator extracts the question
information associated with the attribute information indicating a
different perspective from the perspective of the question, from
the stored question information as the second re-question
information, in a case where the reaction of the customer based on
the biological reaction information is a negative reaction and the
reaction of the customer based on the dialogue content information
is a negative reaction.
9. The proposal candidate presentation device according to claim 6,
wherein a degree of similarity indicating a mutual similarity is
set between the respective perspectives of the attribute
information, and the re-question generator decides the attribute
information having the degree of similarity that is less than a
predetermined value with respect to the perspective of the
question, as the attribute information indicating a different
perspective from the perspective of the question.
10. The proposal candidate presentation device according to claim
1, further comprising: a sensor that detects the biological data of
the customer.
11. The proposal candidate presentation device according to claim
1, further comprising: a microphone that detects the dialogue
content between the customer and the proposer.
12. A proposal candidate presentation method, including: acquiring
biological data of a customer, and generating biological reaction
information including the acquired biological data and first time
information indicating a time at which the biological data was
acquired; acquiring dialogue content between the customer and a
proposer, and generating dialogue content information including
dialogue information indicating the dialogue content and second
time information indicating a time at which the dialogue content
was acquired; determining whether a reaction of the customer
regarding a question asked by the proposer is a positive reaction
or a negative reaction, based on the biological reaction
information, and determining whether the reaction of the customer
regarding the question is a positive reaction or a negative
reaction, based on the dialogue content information; generating
proposal candidate information indicating at least one proposal for
the customer, based on a response of the customer regarding the
question, in a case where it is determined that a reaction of the
customer based on the biological reaction information is a positive
reaction and a reaction of the customer based on the dialogue
content information is a positive reaction; and generating first
re-question information indicating first re-question having a same
perspective as a perspective of the question, in a case where the
reaction of the customer based on the biological reaction
information and the reaction of the customer based on the dialogue
content information do not match.
Description
BACKGROUND
1. Technical Field
[0001] The present disclosure relates to a proposal candidate
presentation device, a proposal candidate presentation method, and
a recording medium having recorded thereon a proposal candidate
presentation program, which present proposal candidate information
including at least one proposal for a customer on the basis of
dialogue content including a question asked to the customer by a
proposer and a response of the customer regarding the question. The
present disclosure relates to a technique for presenting the
proposer with proposal candidate information including a proposal
that corresponds to the preferences of the customer, when the
proposer carries out consulting work, concierge work, and the like
with respect to the customer, face-to-face or via a predetermined
network, in various facilities such as a travel agency and a hotel,
for example.
2. Description of the Related Art
[0002] In recent years, artificial intelligence has advanced and
various consulting work and concierge work such as selling work,
reception work, and guidance work is being carried out using
devices that employ artificial intelligence in retail stores,
banks, travel agencies, hotels, medical facilities, nursing homes,
schools, manufacturing plants, and various other facilities.
[0003] For example, Japanese Unexamined Patent Application
Publication No. 2001-28020 discloses that the state of a user is
recognized by means of a dialogue with the user via an appropriate
input/output device. In addition Japanese Unexamined Patent
Application Publication No. 2001-28020 discloses a travel companion
device that is provided with: a dialogue-type condition extraction
unit that extracts a condition relating to a trip of the user on
the basis of the aforementioned recognition result; a concept
deciding unit that decides the concept of the trip on the basis of
the condition extracted by the dialogue-type condition extraction
unit; and a plan creation unit that creates a plan for the trip in
accordance with the decided concept. In this Japanese Unexamined
Patent Application Publication No. 2001-28020, it is described that
it is possible to easily create a trip plan capable of satisfying a
traveler.
[0004] Furthermore, the following is disclosed in Japanese
Unexamined Patent Application Publication No. 2011-108142.
Specifically, an output screen generation unit generates an output
screen that displays question information, and causes the output
screen to be displayed on a user terminal and presented to a user.
An information acquisition unit acquires response information
indicating a response of the user regarding the question
information, and biological information of the user. An information
storage unit stores the question information, the response
information, and the biological information corresponding to the
response information, in association with each other. A response
determination unit determines whether or not to carry out
re-questioning on the basis of the biological information of the
user corresponding to the response information. In the case where
the response determination unit has determined that re-questioning
is to be carried out, the output screen generation unit generates
an output screen that displays re-question information, and causes
the output screen to be displayed on the user terminal and
presented to the user. In this Japanese Unexamined Patent
Application Publication No. 2011-108142, it is described that waste
is eliminated during profiling by carrying out re-questioning only
for responses in situations that are different from those of past
biological information or response information, and it is possible
to reduce the burden of carrying out profiling many times for the
user.
[0005] Furthermore, the following is disclosed in Japanese
Unexamined Patent Application Publication No. 2002-108183.
Specifically, a teaching material presentation means retrieves
teaching material retained in a teaching material retaining means
and presents the teaching material to a user in accordance with a
teaching material presentation procedure retained in a teaching
material presentation procedure retaining means. At such time, a
user reaction observation means observes a reaction exhibited by
the user, and converts the reaction into numerical information and
records the numerical information as learning history in a learning
history recording means. An optimum teaching material presentation
procedure deciding means decides a teaching material presentation
procedure for which the best reaction has been exhibited up to that
point in time, as the optimum teaching material presentation
procedure, on the basis of the recorded learning history. In this
Japanese Unexamined Patent Application Publication No. 2002-108183,
it is described that it is possible to reflect the reaction of the
user that is exhibited when teaching material is presented, and to
expect an improvement in the learning effect.
SUMMARY
[0006] One non-limiting and exemplary embodiment provides a
technique with which it is possible for a proposer to be presented
with proposal candidate information including a proposal that
corresponds to the preferences of a customer, even in the case
where there is a difference between a reaction determined from a
response of the customer regarding a question and a reaction
determined from biological data of the customer regarding the
question.
[0007] In one general aspect, the techniques disclosed here feature
a proposal candidate presentation device provided with: a
biological reaction information generator that acquires biological
data of a customer, and generates biological reaction information
including the biological data and first time information indicating
a time at which the biological data was acquired; a dialogue
content information generator that acquires dialogue content
between the customer and a proposer, and generates dialogue content
information including dialogue information indicating the dialogue
content and second time information indicating a time at which the
dialogue content was acquired; a countermeasure determiner that
determines whether a reaction of the customer regarding a question
asked by the proposer is a positive reaction or a negative
reaction, based on the biological reaction information, and
determines whether the reaction of the customer regarding the
question is a positive reaction or a negative reaction, based on
the dialogue content information; a proposal candidate generator
that generates proposal candidate information indicating at least
one proposal for the customer, based on a response of the customer
regarding the question, in a case where it is determined that a
reaction of the customer based on the biological reaction
information is a positive reaction and a reaction of the customer
based on the dialogue content information is a positive reaction;
and a re-question generator that generates first re-question
information indicating first re-question having a same perspective
as a perspective of the question, in a case where the reaction of
the customer based on the biological reaction information and the
reaction of the customer based on the dialogue content information
do not match.
[0008] General or specific aspects may be realized by an element, a
device, an apparatus, a system, an integrated circuit, or a method.
Furthermore, general or specific aspects may be realized by an
arbitrary combination of an element, a device, an apparatus, a
system, an integrated circuit, and a method.
[0009] Additional benefits and advantages of the disclosed
embodiments will be apparent from the specification and figures.
The benefits and/or advantages may be individually provided by the
various embodiments or features disclosed in the specification and
figures, and need not all be provided in order to obtain one or
more of the same.
BRIEF DESCRIPTION OF THE DRAWINGS
[0010] FIG. 1 is a block diagram depicting an example of a
configuration of a proposal candidate presentation device according
to an embodiment of the present disclosure;
[0011] FIG. 2 is a flowchart depicting an example of proposal
candidate presentation processing carried out by the proposal
candidate presentation device depicted in FIG. 1; and
[0012] FIG. 3 is a drawing depicting an example of summary
information created from biological reaction information and
dialogue content information.
DETAILED DESCRIPTION
(Findings Forming the Basis for the Present Disclosure)
[0013] In recent years, it is becoming easy to measure brain waves,
heartbeats, blood pressure, gas discharged from the body, and the
like. Furthermore, it is also becoming possible to measure such
biological data in a noninvasive manner, and a situation now exists
in which the psychological state of a customer may be understood
from these measurement items. Consequently, it is becoming clear
whether or not a customer is pleased with a given proposal, and
whether a reaction regarding the proposal is positive or
negative.
[0014] Meanwhile, there exists consulting work and concierge work
in hotels and the like in which products such as trip plans are
proposed and sold face-to-face or via the Internet to customers. In
such work, a proposer engages in a conversation on the basis of the
psychological state of a customer estimated using biological data
and observes the reactions of the customer, and is thereby able to
analyze the likes and dislikes (the preferences) of that customer,
and to make a proposal that is suitable for the preferences. In
this case, it is necessary to accurately judge what kind of
preferences a customer has and for these to be linked to the
optimum proposal.
[0015] However, depending on the customer, there may be cases where
there are differences or inconsistencies between reactions
determined from responses to the same question and reactions
determined from biological data. Meanwhile, in the techniques
disclosed in Japanese Unexamined Patent Application Publication
Nos. 2001-28020, 2011-108142, and 2002-108183, only biological
information is simply used, and no investigation whatsoever is
carried out into the case where there is a difference between a
reaction determined from a response of a customer regarding a
question and a reaction determined from biological data of the
customer regarding the question. Therefore, it is not possible to
carry out an appropriate countermeasure whatsoever for the case
where there is a difference between a reaction determined from a
response of a customer regarding a question and a reaction
determined from biological data of the customer regarding the
question.
[0016] Based on the aforementioned findings, the inventors of the
present application carried out a diligent investigation into a
countermeasure for the case where there is a difference between a
reaction determined from a response of a customer regarding a
question and a reaction determined from biological data of the
customer regarding the question. As a result, the present
disclosure was completed.
[0017] A proposal candidate presentation device according to an
aspect of the present disclosure is provided with: a biological
reaction information generator that acquires biological data of a
customer, and generates biological reaction information including
the biological data and first time information indicating a time at
which the biological data was acquired; a dialogue content
information generator that acquires dialogue content between the
customer and a proposer, and generates dialogue content information
including dialogue information indicating the dialogue content and
second time information indicating a time at which the dialogue
content was acquired; a countermeasure determiner that determines
whether a reaction of the customer regarding a question asked by
the proposer is a positive reaction or a negative reaction, based
on the biological reaction information, and determines whether the
reaction of the customer regarding the question is a positive
reaction or a negative reaction, based on the dialogue content
information; a proposal candidate generator that generates proposal
candidate information indicating at least one proposal for the
customer, based on a response of the customer regarding the
question, in a case where it is determined that a reaction of the
customer based on the biological reaction information is a positive
reaction and a reaction of the customer based on the dialogue
content information is a positive reaction; and a re-question
generator that generates first re-question information indicating
first re-question having a same perspective as a perspective of the
question, in a case where the reaction of the customer based on the
biological reaction information and the reaction of the customer
based on the dialogue content information do not match.
[0018] According to a configuration such as this, biological data
of the customer at a time when the proposer asks a question to the
customer is acquired, and biological reaction information including
the acquired biological data and biological time information
indicating the time at which the biological data was acquired is
generated. Together therewith, dialogue content between the
customer and the proposer at a time when the proposer asks the
question to the customer is acquired, and dialogue content
information including dialogue information indicating the acquired
dialogue content and dialogue time information indicating the time
at which the dialogue content was acquired is generated.
Furthermore, whether the reaction of the customer regarding the
question is a positive reaction or a negative reaction is
determined on the basis of the biological reaction information.
Together therewith, whether the reaction of the customer regarding
the question is a positive reaction or a negative reaction is
determined on the basis of the dialogue content information. In the
case where, as determination results, the reaction of the customer
based on the biological reaction information is a positive reaction
and the reaction of the customer based on the dialogue content
information is a positive reaction, proposal candidate information
based on the response of the customer regarding the question asked
to the customer by the proposer is generated.
[0019] Consequently, in the case where the reaction of the customer
based on the biological reaction information and the reaction of
the customer based on the dialogue content information are both
positive reactions, it is possible for an item that is liked by the
customer to be reliably determined from the response of the
customer regarding the question asked to the customer by the
proposer. In addition, by generating proposal candidate information
based on this response of the customer, proposal candidate
information including a proposal that is liked by the customer can
be appropriately presented to the proposer.
[0020] Furthermore, in the case where, as determination results,
the reaction of the customer based on the biological reaction
information and the reaction of the customer based on the dialogue
content information do not match, first re-question information
representing first re-question having the same perspective as that
of the question included in the dialogue content is generated.
[0021] Consequently, the proposer is able to carry out first
re-question having the same perspective using the first re-question
information, even in the case where the reaction of the customer
based on the biological reaction information and the reaction of
the customer based on the dialogue content information do not
match, and an item liked by the customer cannot be accurately
determined from the response of the customer regarding the question
asked to the customer by the proposer. Thus, it is possible for an
item that is liked by the customer to be accurately determined from
a response of the customer regarding the first re-question having
the same perspective, in the case where a reaction of the customer
based on biological reaction information and a reaction of the
customer based on dialogue content information regarding this first
re-question are both positive reactions. In addition, proposal
candidate information including a proposal that is liked by the
customer can be appropriately presented to the proposer.
[0022] As a result, proposal candidate information including a
proposal that corresponds to the preferences of the customer can be
presented to the proposer even in the case where there is a
difference between a reaction determined from a response of the
customer regarding a question and a reaction determined from
biological data of the customer regarding the question.
[0023] The aforementioned proposal candidate presentation device
may be further provided with a proposal candidate storer that
stores the proposal candidate information, which is set in advance
with respect to the question, and the proposal candidate generator
may extract the proposal candidate information that has been set
with respect to the question, from the proposal candidate storer,
in a case where it is determined that the reaction of the customer
based on the biological reaction information is a positive reaction
and the reaction of the customer based on the dialogue content
information is a positive reaction.
[0024] According to a configuration such as this, proposal
candidate information that has been set with respect to a question
asked to the customer by the proposer is extracted from the
proposal candidate storer in the case where the reaction of the
customer based on the biological reaction information is a positive
reaction and the reaction of the customer based on the dialogue
content information is a positive reaction. It is thereby possible
to extract and present proposal candidate information including a
proposal which is suitable for an item that is liked by the
customer, assumed from the response of the customer regarding the
question asked to the customer by the proposer.
[0025] The proposal candidate presentation device may be further
provided with a question storer that stores, in association with
each other, question information indicating each of a plurality of
questions including the question, and attribute information
indicating a perspective of each of the plurality of questions, and
the re-question generator may extract the question information
associated with the attribute information indicating a same
perspective as the perspective of the question, from the stored
question information as the first re-question information, in a
case where the reaction of the customer based on the biological
reaction information and the reaction of the customer based on the
dialogue content information do not match.
[0026] According to a configuration such as this, question
information having associated therewith attribute information
indicating the same perspective as the perspective of the question
included in the dialogue content is extracted from the stored
question information as the first re-question information in the
case where the reaction of the customer based on the biological
reaction information and the reaction of the customer based on the
dialogue content information do not match. Thus, first re-question
information having attribute information having the same
perspective as that of the question asked to the customer by the
proposer can be presented to the proposer even in the case where an
item liked by the customer cannot be accurately determined from a
response of the customer regarding the question asked to the
customer by the proposer. Consequently, an item that is liked by
the customer can be accurately determined from the response of the
customer regarding the first re-question having the same
perspective.
[0027] In the aforementioned proposal candidate presentation
device, a degree of similarity indicating a mutual similarity may
be set between the respective perspectives of the attribute
information, and the re-question generator may decide the attribute
information having the degree of similarity that is equal to or
greater than a predetermined value with respect to the perspective
of the question, as the attribute information indicating the same
perspective as the perspective of the question.
[0028] According to a configuration such as this, attribute
information having a degree of similarity that is equal to or
greater than a predetermined value with respect to the perspective
of the question included in the dialogue content is decided as
attribute information indicating the same perspective as the
perspective of the question included in the dialogue content. It is
thereby possible to extract first re-question information
representing a question having a similar perspective.
[0029] In the aforementioned proposal candidate presentation
device, the re-question generator may generate second re-question
information indicating second re-question having a different
perspective from the perspective of the question included in the
dialogue content, when a case where the reaction of the customer
based on the biological reaction information and the reaction of
the customer based on the dialogue content information do not match
has been repeated a predetermined number of times with respect to
the first re-question indicated by the first re-question
information.
[0030] According to a configuration such as this, second
re-question information representing second re-question having a
different perspective from the perspective of the question included
in the dialogue content is generated when the case where the
reaction of the customer based on the biological reaction
information and the reaction of the customer based on the dialogue
content information do not match has been repeated a predetermined
number of times with respect to a question represented by the first
re-question information. Thus, second re-question information
having a different perspective from that of the question asked to
the customer by the proposer can be presented to the proposer in
the case where a state has continued in which an item that is liked
by the customer cannot be accurately determined from the response
of the customer regarding the question asked to the customer by the
proposer. Consequently, an item that is liked by the customer can
be accurately determined from the response of the customer
regarding the second re-question having a different
perspective.
[0031] The aforementioned proposal candidate presentation device
may be further provided with a question storer that stores, in
association with each other, question information indicating each
of a plurality of questions including the question, and attribute
information indicating a perspective of each of the plurality of
questions, and the re-question generator may extract the question
information associated with the attribute information indicating a
different perspective from the perspective of the question, from
the stored question information as the second re-question
information, when a case where the reaction of the customer based
on the biological reaction information and the reaction of the
customer based on the dialogue content information do not match has
been repeated a predetermined number of times with respect to the
first re-question indicated by the first re-question
information.
[0032] According to a configuration such as this, question
information having associated therewith attribute information
indicating a different perspective from the perspective of the
question included in the dialogue content is extracted from the
stored question information as second re-question information when
the case where the reaction of the customer based on the biological
reaction information and the reaction of the customer based on the
dialogue content information do not match has been repeated a
predetermined number of times with respect to the question
represented by the first re-question information. Thus, second
re-question information having attribute information having a
different perspective from that of the question asked to the
customer by the proposer can be presented to the proposer in the
case where a state has continued in which an item that is liked by
the customer cannot be accurately determined from the response of
the customer regarding the question asked to the customer by the
proposer. Consequently, an item that is liked by the customer can
be accurately determined from the response of the customer
regarding the second re-question having a different
perspective.
[0033] In the aforementioned proposal candidate presentation
device, the re-question generator may generate second re-question
information indicating second re-question having a different
perspective from the perspective of the question, in a case where
the reaction of the customer based on the biological reaction
information is a negative reaction and the reaction of the customer
based on the dialogue content information is a negative
reaction.
[0034] According to a configuration such as this, second
re-question information representing second re-question having a
different perspective from that of the question included in the
dialogue content is generated in the case where the reaction of the
customer based on the biological reaction information is a negative
reaction and the reaction of the customer based on the dialogue
content information is a negative reaction.
[0035] Consequently, the proposer is able to carry out second
re-question having a different perspective using the second
re-question information, even in the case where the reaction of the
customer based on the biological reaction information and the
dialogue content information is a negative reaction, and an item
liked by the customer cannot be determined from the response of the
customer regarding the question asked to the customer by the
proposer. Thus, it is possible for an item that is liked by the
customer to be accurately determined from a response of the
customer regarding the second re-question having a different
perspective, in the case where the reaction of the customer based
on the biological reaction information and the reaction of the
customer based on the dialogue content information regarding this
second re-question are both positive reactions. Consequently,
proposal candidate information including a proposal that is liked
by the customer can be appropriately presented to the proposer.
[0036] The aforementioned proposal candidate presentation may be
further provided with a question storer that stores, in association
with each other, question information indicating each of a
plurality of questions including the question, and attribute
information indicating a perspective of each of the plurality of
questions, and the re-question generator may extract the question
information associated with the attribute information indicating a
different perspective from the perspective of the question, from
the stored question information as the second re-question
information, in a case where the reaction of the customer based on
the biological reaction information is a negative reaction and the
reaction of the customer based on the dialogue content information
is a negative reaction.
[0037] According to a configuration such as this, question
information having associated therewith attribute information
indicating a different perspective from the perspective of the
question included in the dialogue content is extracted from the
stored question information as the second re-question information
in the case where the reaction of the customer based on the
biological reaction information is a negative reaction and the
reaction of the customer based on the dialogue content information
is a negative reaction. Thus, second re-question information having
attribute information having a different perspective from that of
the question asked to the customer by the proposer can be presented
to the proposer even in the case where an item liked by the
customer cannot be determined from a response of the customer
regarding the question asked to the customer by the proposer.
Consequently, an item that is liked by the customer can be
accurately determined from the response of the customer regarding
the second re-question having a different perspective.
[0038] In the aforementioned proposal candidate presentation
device, a degree of similarity indicating a mutual similarity may
be set between the respective perspectives of the attribute
information, and the re-question generator may decide the attribute
information having the degree of similarity that is less than a
predetermined value with respect to the perspective of the
question, as the attribute information indicating a different
perspective from the perspective of the question.
[0039] According to a configuration such as this, attribute
information having a degree of similarity that is less than a
predetermined value with respect to the perspective of the question
included in the dialogue content is decided as attribute
information indicating a different perspective from the perspective
of the question included in the dialogue content. It is thereby
possible to extract second re-question information representing a
question having a perspective that is similar to an extent, from
among different perspectives.
[0040] Furthermore, the present disclosure can not only be realized
as a proposal candidate presentation device provided with
characteristic configurations such as the aforementioned, but can
also be realized as a proposal candidate presentation method or the
like for executing characteristic processing corresponding to the
characteristic configurations provided in the proposal candidate
presentation device. Furthermore, it is also possible for the
present disclosure to be realized as a recording medium having
recorded thereon a computer program that causes a computer to
execute the characteristic processing included in a proposal
candidate presentation method such as the aforementioned.
Consequently, an effect similar to that of the aforementioned
proposal candidate presentation device can be demonstrated also in
the other aspects described below.
[0041] A proposal candidate presentation method according to
another aspect of the present disclosure includes: acquiring
biological data of a customer, and generating biological reaction
information including the acquired biological data and first time
information indicating a time at which the biological data was
acquired; acquiring dialogue content between the customer and a
proposer, and generating dialogue content information including
dialogue information indicating the dialogue content and second
time information indicating a time at which the dialogue content
was acquired; determining whether a reaction of the customer
regarding a question asked by the proposer is a positive reaction
or a negative reaction, based on the biological reaction
information, and determining whether the reaction of the customer
regarding the question is a positive reaction or a negative
reaction, based on the dialogue content information; generating
proposal candidate information indicating at least one proposal for
the customer, based on a response of the customer regarding the
question, in a case where it is determined that a reaction of the
customer based on the biological reaction information is a positive
reaction and a reaction of the customer based on the dialogue
content information is a positive reaction; and generating first
re-question information indicating first re-question having a same
perspective as a perspective of the question; in a case where the
reaction of the customer based on the biological reaction
information and the reaction of the customer based on the dialogue
content information do not match.
[0042] A recording medium according to another aspect of the
present disclosure has recorded thereon a proposal candidate
presentation program that causes a computer to execute processing
including: acquiring biological data of a customer, and generating
biological reaction information including the acquired biological
data and first time information indicating a time at which the
biological data was acquired; acquiring dialogue content between
the customer and a proposer, and generating dialogue content
information including dialogue information indicating the dialogue
content and second time information indicating a time at which the
dialogue content was acquired; determining whether a reaction of
the customer regarding a question asked by the proposer is a
positive reaction or a negative reaction, based on the biological
reaction information, and determining whether the reaction of the
customer regarding the question is a positive reaction or a
negative reaction, based on the dialogue content information;
generating proposal candidate information indicating at least one
proposal for the customer, based on a response of the customer
regarding the question, in a case where it is determined that a
reaction of the customer based on the biological reaction
information is a positive reaction and a reaction of the customer
based on the dialogue content information is a positive reaction;
and generating first re-question information indicating first
re-question having a same perspective as a perspective of the
question, in a case where the reaction of the customer based on the
biological reaction information and the reaction of the customer
based on the dialogue content information do not match.
[0043] Also, it goes without saying a computer program such as the
aforementioned can be distributed by way of a computer-readable
non-transitory recording medium such as a CD-ROM or a communication
network such as the Internet.
[0044] Furthermore, the present disclosure may be configured as a
system in which some constituent elements of a proposal candidate
presentation device according to an embodiment of the present
disclosure and other constituent elements are distributed among a
plurality of computers.
[0045] It should be noted that the embodiments described
hereinafter are all intended to represent exemplary embodiments of
the present disclosure. The numerical values, the shapes, the
constituent elements, the steps, the order of the steps, and the
like given in the following embodiments are examples and are not
intended to restrict the present disclosure. Furthermore, from
among the constituent elements in the following embodiments,
constituent elements that are not mentioned in the independent
claims indicating the most significant concepts are described as
optional constituent elements. Furthermore, in all of the
embodiments, it is also possible to combine the respective content
thereof.
Embodiments
[0046] Hereinafter, embodiments of the present disclosure will be
described with reference to the drawings. FIG. 1 is a block diagram
depicting an example of a configuration of a proposal candidate
presentation device according to an embodiment of the present
disclosure. The proposal candidate presentation device depicted in
FIG. 1 is provided with a biological data measurement unit 11, a
dialogue content acquisition unit 12, a countermeasure
determination unit 13, a question storage unit 14, a question
generation unit 15, a proposal candidate storage unit 16, a
proposal candidate generation unit 17, and a presentation unit
18.
[0047] The proposal candidate presentation device depicted in FIG.
1 is used when a proposal that corresponds to the preferences of a
customer is made while a proposer engages in a dialogue with the
customer. The proposal candidate presentation device depicted in
FIG. 1 is configured from, for example, a tablet having a touch
panel, a speaker, a microphone, a central processing unit (CPU), a
read-only memory (ROM), a random-access memory (RAM), an auxiliary
storage device, or the like. This proposal candidate presentation
device presents proposal candidate information including at least
one proposal for the customer; on the basis of dialogue content
which includes a question asked to the customer by the proposer and
a response of the customer regarding the question, and biological
data of the customer. Together therewith; this proposal candidate
presentation device presents first or second re-question
information representing first or second re-question for the
customer.
[0048] It should be noted that the configuration of the proposal
candidate presentation device depicted in FIG. 1 is not
particularly restricted to the aforementioned example of a tablet,
and another device such as a mobile terminal, a smartphone for
example; or a stationary or mobile personal computer may be
used.
[0049] Furthermore, in the present embodiment, an example in which
a proposer engages in a dialogue face-to-face with a customer is
described; however, the present disclosure is not particularly
restricted to this example, and can be similarly applied also in
the case where the proposer engages in a dialogue with the customer
via a network such as the Internet. In this case; the customer also
uses a device such as a tablet or a personal computer. The device
of the customer is provided with the aforementioned biological data
measurement unit, a predetermined communication unit, or the like,
the device of the proposer is provided with a predetermined
communication unit or the like, and biological data or the like is
transmitted from the device of the customer to the device of the
proposer.
[0050] The biological data measurement unit 11 measures and
acquires biological data of the customer at a time when the
proposer asks a question to the customer. The biological data
measurement unit 11 generates biological reaction information
(sensing information) including the acquired biological data and
biological time information indicating the time at which the
biological data was acquired, and outputs the biological reaction
information to the countermeasure determination unit 13. Brain
waves, biogas, blood pressure, respiration, heartbeat, and/or body
temperature or the like fall under biological data. For example,
the biological data measurement unit 11 is provided with a sensor
that measures human pulse waves in a non-contact manner using a
high sensitive spread-spectrum millimeter-wave radar or the like,
and detects the heart rate and heartbeat fluctuations of the
customer.
[0051] It should be noted that the configuration of the biological
data measurement unit 11 is not particularly restricted to this
example, and the customer may attach a wearable terminal such as a
smartwatch that measures biological data of the customer, and
biological data may be acquired from the wearable terminal. In this
case, the biological data measurement unit 11 constitutes a
biological data acquisition unit that acquires measured biological
data.
[0052] Furthermore, the data that is acquired by the biological
data measurement unit 11 is also not particularly restricted to the
aforementioned examples, and other biological data such as the
speech, facial images, and blood oxygen concentration of the
customer may be used as long as it is possible to determine whether
a reaction of the customer that is described later on is a positive
reaction or a negative reaction. In this case, the biological data
measurement unit 11 is configured in such a way as to measure each
item of biological data.
[0053] The dialogue content acquisition unit 12 acquires dialogue
content between the customer and the proposer at a time when the
proposer asks a question to the customer. The dialogue content
acquisition unit 12 generates dialogue content information
(exchange information) including dialogue information indicating
the aforementioned dialogue content and dialogue time information
indicating the time at which dialogue content was acquired, and
outputs the dialogue content information to the countermeasure
determination unit 13. Specifically, the dialogue content
acquisition unit 12 is configured from a microphone or the like,
and acquires speech of the dialogue content between the proposer
and the customer. The dialogue content acquisition unit 12 subjects
the acquired speech to speech recognition and generates text data
that is made up of character strings, which is set as the dialogue
content information together with the dialogue information that is
made up of text data or the like indicating the dialogue content
and the dialogue time information indicating the time at which the
dialogue content was acquired.
[0054] It should be noted that the customer also uses a device such
as a tablet or a personal computer in the case where the proposer
engages in a dialogue with the customer via a network such as the
Internet. The device of the customer is provided with a microphone,
a predetermined communication unit, or the like, the device of the
proposer is provided with a predetermined communication unit or the
like, and speech data or the like including responses of the
customer is transmitted from the device of the customer to the
device of the proposer.
[0055] The countermeasure determination unit 13 determines whether
a reaction of the customer regarding a question of the proposer is
a positive reaction or a negative reaction, on the basis of the
biological reaction information. Together therewith, the
countermeasure determination unit 13 determines whether the
reaction of the customer regarding the question of the proposer is
a positive reaction or a negative reaction, on the basis of the
dialogue content information. Specifically, as a first
determination result, the countermeasure determination unit 13
determines whether the biological reaction information indicates a
positive reaction or a negative reaction. Furthermore, as a second
determination result, the countermeasure determination unit 13
determines whether the dialogue content information indicates a
positive reaction or a negative reaction, combines the first
determination result and the second determination result, and
determines which from among proposal candidate presenting, first
re-questioning, or second re-questioning is to be carried out as a
countermeasure for the proposer.
[0056] Here, the following method can be used as an example of a
method for determining whether the reaction of the customer is a
positive reaction or a negative reaction.
[0057] First, as a method for determining a reaction of the
customer using biological data, for example, the countermeasure
determination unit 13 analyzes biological data acquired by the
biological data measurement unit 11, and thereby estimates the
emotion of customer (for example, see Japanese Patent No. 5257525).
The countermeasure determination unit 13 determines a positive
reaction in the case where the emotion of the customer is
"pleasure" or "relaxation", and determines a negative reaction in
the case where the emotion of the customer is "anger" or
"sadness".
[0058] Specifically, in the case where heartbeat fluctuations
acquired by the biological data measurement unit 11 are equal to or
higher than a predetermined value, the emotion of the customer
becomes "pleasure" or "relaxation", and the countermeasure
determination unit 13 determines a positive reaction. However, in
the case where the heartbeat fluctuations acquired by the
biological data measurement unit 11 are lower than the
predetermined value, the emotion of the customer becomes "anger" or
"sadness", and the countermeasure determination unit 13 determines
a negative reaction.
[0059] It should be noted that the method for determining a
reaction of the customer using biological data is not particularly
restricted to the aforementioned example, and various alterations
are possible. For example, the emotion of the customer may be
specified using the degree of wakefulness and degree of comfort of
the customer generated from biological sensor values (see Japanese
Patent No. 5735592), and the specified emotion may be associated
with a positive reaction or a negative reaction.
[0060] Next, as a method for determining a reaction of the customer
using dialogue information, for example, artificial intelligence
such as deep learning is used for the countermeasure determination
unit 13 to judge a positive reaction in the case where the response
of the customer is interpreted as being "yes" and to determine a
negative reaction in the case where the response of the customer is
interpreted as being "no" from dialogue information. It should be
noted that the method for determining a reaction of the customer
using dialogue information is not particularly restricted to the
aforementioned example, and various alterations are possible.
[0061] A plurality of questions for estimating the preferences of
the customer are stored in the question storage unit 14, and tag
information indicating the "perspective" of a question is assigned
to each question. Specifically, the question storage unit 14
associates question information representing a question for
estimating the preferences of the customer, and attribute
information indicating the perspective of that question, and
stores, in advance, a plurality of items of question information
and a plurality of items of attribute information.
[0062] Here, the "perspective" means the point of view adopted when
considering and judging a matter in an analysis, discussion, or the
like. For example, in the case where the proposer proposes a trip
plan for the customer in a travel agency as a consultant, "city
name", "architecture", "dining", "music", "shopping", or the like
are tag information indicating "perspectives". In this case, the
attribute information of "city name" is associated with questions
relating to "Rome", "Naples", "Venice", or the like, the attribute
information of "architecture" is associated with questions relating
to the "Sagrada Familia", the "Notre-Dame Cathedral", the "Leaning
Tower of Pisa", or the like, the attribute information of "dining"
is associated with questions relating to "French cuisine", "Italian
cuisine", "Chinese cuisine", or the like, and the attribute
information of "music" is associated with questions relating to
"opera", "classical music", "rock", or the like. It should be noted
that the attribute information is not particularly restricted to
the aforementioned examples, and various alterations are possible
according to the proposal content of the proposer.
[0063] The question generation unit 15 refers to the question
storage unit 14, and creates a question for estimating the
preferences of the customer, or creates a question that corresponds
to a determination result that is output from the countermeasure
determination unit 13.
[0064] First, as initial setting processing, the question
generation unit 15 extracts question information representing a
question to be an initial question, from the question information
stored in the question storage unit 14 on the basis of information
such as the past history and profile of the customer, and outputs
the question information to the presentation unit 18. For example,
in the case where information such as the past history and profile
of the customer is stored in advance in a memory (not depicted)
inside the question generation unit 15, the question generation
unit 15 uses identification information or the like of the customer
to read, from the memory, information such as the past history and
profile of the customer being dealt with by the proposer, extracts
question information to be the initial question on the basis of the
information or the like that has been read, and outputs the
question information to the presentation unit 18. It should be
noted that the information such as the past history and profile of
the customer is not particularly restricted to the aforementioned
example, and this information may be stored in an external server
or the like and obtained from the server or the like via a
predetermined network.
[0065] Furthermore, in the case where the determination result of
the countermeasure determination unit 13 is first re-questioning,
the question generation unit 15 generates first re-question
information indicating the same perspective as that of the previous
question and outputs the first re-question information to the
presentation unit 18. Here, the case where the determination result
of the countermeasure determination unit 13 is first re-questioning
means the case where the determination based on the biological
reaction information is a positive reaction and the determination
based on the dialogue content information is a negative reaction,
or the case where the determination based on the biological
reaction information is a negative reaction and the determination
based on the dialogue content information is a positive reaction.
Furthermore, in the case where the determination result of the
countermeasure determination unit 13 is second re-questioning, the
question generation unit 15 generates second re-question
information indicating a different perspective from that of the
previous question and outputs the second re-question information to
the presentation unit 18. Here, the case where the determination
result of the countermeasure determination unit 13 is second
re-questioning means the case where the determination based on the
biological reaction information is a negative reaction and the
determination based on the dialogue content information is a
negative reaction.
[0066] Specifically, the question generation unit 15 extracts
question information having associated therewith attribute
information indicating the same perspective as the perspective of
the question included in the dialogue content, from the question
information stored in the question storage unit 14 as first
re-question information in the case where the reaction of the
customer based on the biological reaction information and the
reaction of the customer based on the dialogue content information
do not match. The question generation unit 15 thereby generates
first re-question information representing first re-question having
the same perspective as that of the question included in the
dialogue content.
[0067] Here, the attribute information may have a degree of
similarity between the perspective of that attribute information
and the perspective of other attribute information. In this case,
the question generation unit 15 decides attribute information that
has a degree of similarity that is equal to or greater than a
predetermined value with respect to the perspective of the question
included in the dialogue content, as attribute information
indicating the same perspective as the perspective of the question
included in the dialogue content. In addition, the question
generation unit 15 extracts the question information associated
with the decided attribute information, from the question
information stored in the question storage unit 14 as first
re-question information.
[0068] For example, in the case where the proposer proposes a trip
plan for the customer in a travel agency as a consultant, it is
assumed that "city name", "dining", "music", and "shopping" are set
as attribute information. In this case, when the degree of
similarity between "city name" and "dining" is 0.8, the degree of
similarity between "city name" and "music" is 0.4, the degree of
similarity between "city name" and "shopping" is 0.6, and a
determination reference value is 0.7, attribute information with
which the degree of similarity is equal to or greater than 0.7 may
be decided as attribute information having the same perspective. In
this case, the degree of similarity between "city name" and
"dining" is 0.8, which is equal to or greater than the
determination reference value of 0.7, and therefore the perspective
of question information having "city name" as attribute information
becomes the same as the perspective of question information having
"dining" as attribute information. It should be noted that the
attribute information and the determination reference value are not
particularly restricted to the aforementioned example, and various
alterations are possible according to the proposal content of the
proposer.
[0069] Furthermore, it is assumed that the case where the reaction
of the customer based on the biological reaction information and
the reaction of the customer based on the dialogue content
information do not match is repeated a predetermined number of
times with respect to questions represented by the first
re-question information. In this case, the question generation unit
15 extracts question information having associated therewith
attribute information indicating a different perspective from the
perspective of the question included in the dialogue content, from
the question information stored in the question storage unit 14 as
second re-question information. The question generation unit 15
thereby generates second re-question information representing
second re-question having a different perspective from the
perspective of the question included in the dialogue content.
[0070] Furthermore, it is assumed that the reaction of the customer
based on the biological reaction information is a negative reaction
and that the reaction of the customer based on the dialogue content
information is a negative reaction. In this case, the question
generation unit 15 extracts question information having associated
therewith attribute information indicating a different perspective
from the perspective of the question included in the dialogue
content, from the question information stored in the question
storage unit 14 as second re-question information. The question
generation unit 15 thereby generates second re-question information
representing second re-question having a different perspective from
that of the question included in the dialogue content.
[0071] Here, the attribute information may have a degree of
similarity between the perspective of that attribute information
and the perspective of other attribute information. In this case,
the question generation unit 15 decides attribute information that
has a degree of similarity that is less than a predetermined value
with respect to the perspective of the question included in the
dialogue content, as attribute information indicating a different
perspective from the perspective of the question included in the
dialogue content. In addition, the question generation unit 15
extracts the question information associated with the decided
attribute information, from the question information stored in the
question storage unit 14 as second re-question information.
[0072] For example, in the case where the proposer proposes a trip
plan for the customer in a travel agency as a consultant, it is
assumed that "city name", "dining", "music", and "shopping" are set
as attribute information. In this case, when the degree of
similarity between "city name" and "dining" is 0.8, the degree of
similarity between "city name" and "music" is 0.4, the degree of
similarity between "city name" and "shopping" is 0.6, and the
determination reference value is 0.5, attribute information with
which the degree of similarity is less than 0.5 may be decided as
attribute information having a different perspective. In this case,
the degree of similarity between "city name" and "music" is 0.4,
which is less than the determination reference value of 0.5, and
therefore the perspective of question information having "city
name" as attribute information is different from the perspective of
question information having "music" as attribute information.
[0073] It should be noted that the method for acquiring question
information, attribute information, and the like is not
particularly restricted to the aforementioned example. For example,
the question storage unit 14 may be omitted, and the question
information, attribute information, and the like may be stored in
an external server or the like and obtained from the server or the
like via a predetermined network.
[0074] The proposal candidate storage unit 16 stores proposal
candidate information including at least one proposal that has been
set in advance with respect to each of a plurality of questions
that are asked to the customer by the proposer.
[0075] On the basis of question information representing a question
for which it has been determined that the reaction of the customer
based on the biological reaction information is a positive reaction
and the reaction of the customer based on the dialogue content
information is a positive reaction, the proposal candidate
generation unit 17 generates proposal candidate information
including a proposal that is suitable for the customer who has
expressed a positive reaction to that question, and outputs the
proposal candidate information to the presentation unit 18.
[0076] Specifically, the proposal candidate generation unit 17
extracts proposal candidate information that has been set with
respect to the question asked to the customer by the proposer, from
the proposal candidate storage unit 16 in the case where the
reaction of the customer based on the biological reaction
information is a positive reaction and the reaction of the customer
based on the dialogue content information is a positive reaction.
The proposal candidate generation unit 17 thereby generates
proposal candidate information based on the response of the
customer regarding the question asked to the customer by the
proposer.
[0077] It should be noted that the method for acquiring proposal
candidate information or the like is not particularly restricted to
the aforementioned example. For example, the proposal candidate
storage unit 16 may be omitted, and the proposal candidate
information or the like may be stored in an external server or the
like and obtained from the server or the like via a predetermined
network.
[0078] The presentation unit 18, for example, is configured from a
display device or the like, and displays proposal candidate
information including one or more proposals to the proposer.
Furthermore, the presentation unit 18 displays the first
re-question information having the same perspective as the question
included in the dialogue content or the second re-question
information having a different perspective therefrom. Here, in the
case where proposal candidate information including one proposal is
displayed, the proposer proposes that proposal to the customer.
Furthermore, in the case where proposal candidate information
including a plurality of proposals is displayed, the proposer
selects one from among the plurality of proposals on the basis of a
judgment made by the proposer, and proposes the selected proposal
to the customer. It should be noted that the configuration of the
presentation unit 18 is not particularly restricted to the
aforementioned example. For example, an audio output device such as
a speaker, an earphone, or the like may be used, and in this case,
the proposal candidate information is presented to the proposer by
means of audio.
[0079] Next, proposal candidate presentation processing carried out
by the proposal candidate presentation device configured as
mentioned above will be described. FIG. 2 is a flowchart depicting
an example of proposal candidate presentation processing carried
out by the proposal candidate presentation device depicted in FIG.
1.
[0080] The proposer engages in an initial conversation with the
customer, and identification information of the customer is set in
the question generation unit 15. As depicted in FIG. 2, first, as
initial setting processing, the question generation unit 15
extracts question information representing a question that is to be
the initial question, from the question information stored in the
question storage unit 14, on the basis of information such as the
past history and profile of the customer, and outputs the question
information to the presentation unit 18. The presentation unit 18
displays the question information representing the question that is
to be the initial question (step S11).
[0081] Next, the dialogue content acquisition unit 12 acquires
dialogue content between the customer and the proposer (step S12).
The dialogue content acquisition unit 12 generates dialogue content
information including dialogue information indicating this dialogue
content and dialogue time information indicating the time at which
the dialogue content was acquired, and outputs the dialogue content
information to the countermeasure determination unit 13 (step
S13).
[0082] Next, the biological data measurement unit 11 acquires the
pulse of the customer, for example, as biological data (step S14).
The biological data measurement unit 11 generates biological
reaction information including the acquired biological data and
biological time information indicating the time at which the
biological data was acquired, and outputs the biological reaction
information to the countermeasure determination unit 13 (step
S15).
[0083] It should be noted that the order of the processing of steps
S12 and S13 and the processing of steps S14 and S15 are not
particularly restricted to the aforementioned example. For example,
the processing of steps S12 and S13 may be executed after the
processing of steps S14 and S15 or may be executed in parallel.
[0084] Next, the countermeasure determination unit 13 determines
whether a reaction of the customer regarding the question of the
proposer is a positive reaction or a negative reaction, on the
basis of the biological reaction information that has been input.
Together therewith, the countermeasure determination unit 13
determines whether the reaction of the customer regarding the
question of the proposer is a positive reaction or a negative
reaction, on the basis of the dialogue content information that has
been input. In addition, the countermeasure determination unit 13
determines which of the following states (1) to (3) is in effect
(step 316). (1) The determination based on the biological reaction
information is a positive reaction and the determination based on
the dialogue content information is a positive reaction (the
determination results match as positive). (2) The determination
based on the biological reaction information is a positive reaction
and the determination based on the dialogue content information is
a negative reaction, or the determination based on the biological
reaction information is a negative reaction and the determination
based on the dialogue content information is a positive reaction
(the determination results do not match). (3) The determination
based on the biological reaction information is a negative reaction
and the determination based on the dialogue content information is
a negative reaction (the determination results match as
negative).
[0085] In the case of the aforementioned (2) (in the case where the
determination results do not match in step S16), the countermeasure
determination unit 13 notifies the question generation unit 15 that
the determination results do not match and first re-question is to
be carried out. The question generation unit 15 counts the number
of times that the determination results have not matched, and
judges whether or not the number of times that the determination
results have not matched has continued for a predetermined number
of times (for example, three times) (step S17).
[0086] If the case where the determination results do not match has
not continued for the predetermined number of times (no in step
S17), the question generation unit 15 extracts question information
having associated therewith attribute information indicating the
same perspective as the perspective of the question included in the
dialogue content, from the question information stored in the
question storage unit 14 as first re-question information. In
addition, the question generation unit 15 generates first
re-question information representing first re-question having the
same perspective as that of the question included in the dialogue
content, and outputs the first re-question information to the
presentation unit 18 (step S18).
[0087] Next, the presentation unit 18 displays the first
re-question information having the same perspective as the
perspective of the question included in the dialogue content, and,
thereafter, processing transitions to step 312 in order to prepare
for the next dialogue (step S19). Consequently, in the case where
the determination results based on the biological reaction
information and the dialogue content information do not match and
the preferences of the customer cannot be determined, the proposer
is able to carry out re-question in accordance with the first
re-question information having the same perspective as the
perspective of the immediately preceding question, and is able to
accurately confirm the preferences of the customer.
[0088] However, if the case where the determination results do not
match has continued for the predetermined number of times (yes in
step 317), the question generation unit 15 extracts question
information having associated therewith attribute information
indicating a different perspective from the perspective of the
question included in the dialogue content, from the question
information stored in the question storage unit 14 as second
re-question information. In addition, the question generation unit
15 generates second re-question information representing second
re-question having a different perspective from that of the
question included in the dialogue content, from the extracted
question information, and outputs the second re-question
information to the presentation unit 18 (step S20).
[0089] Next, the presentation unit 18 displays the second
re-question information having a different perspective from the
perspective of the question included in the dialogue content, and,
thereafter, processing transitions to step S12 in order to prepare
for the next dialogue (step S19). Consequently, when the case where
the determination results based on the biological reaction
information and the dialogue content information do not match
continues and the preferences of the customer cannot be determined
by means of a question having the same perspective, the proposer is
able to carry out re-question in accordance with the second
re-question information having a different perspective from the
perspective of the question, and is able to accurately confirm the
preferences of the customer by means of a new question.
[0090] Furthermore, in the case of the aforementioned (3) (in the
case where the determination results match as negative in step
S16), the countermeasure determination unit 13 notifies the
question generation unit 15 that the determination results match as
negative and second re-question is to be carried out. The question
generation unit 15 extracts question information having associated
therewith attribute information indicating a different perspective
from the perspective of the question included in the dialogue
content, from the question information stored in the question
storage unit 14 as second re-question information. In addition, the
question generation unit 15 generates second re-question
information representing second re-question having a different
perspective from that of the question included in the dialogue
content, from the extracted question information, and outputs the
second re-question information to the presentation unit 18 (step
320).
[0091] Next, the presentation unit 18 displays the second
re-question information having a different perspective from the
perspective of the question included in the dialogue content, and,
thereafter, processing transitions to step S12 in order to prepare
for the next dialogue (step S19). Consequently, in the case where
the determination results based on the biological reaction
information and the dialogue content information match as negative
and the preferences of the customer cannot be determined by means
of a question having the same perspective, the proposer is able to
carry out re-question in accordance with the second re-question
information having a different perspective from the perspective of
the question, and is able to accurately confirm the preferences of
the customer by means of a new question.
[0092] In addition, in the case of the aforementioned (1) (in the
case where the determination results match as positive in step
S16), the countermeasure determination unit 13 notifies the
proposal candidate generation unit 17 that the determination
results match as positive and a proposal candidate is to be
presented. The proposal candidate generation unit 17 extracts
proposal candidate information that has been set with respect to
the question asked to the customer by the proposer, from the
proposal candidate storage unit 16. In addition, the proposal
candidate generation unit 17 generates the best proposal candidate
information with respect to the response of the customer regarding
the question asked to the customer by the proposer, and outputs the
proposal candidate information to the presentation unit 18 (step
S21).
[0093] Next, the presentation unit 18 displays the best proposal
candidate information with respect to the response of the customer
regarding the question asked to the customer by the proposer, and
processing ends (step S22). Consequently, in the case where the
determination results based on the biological reaction information
and the dialogue content information match as positive and the
preferences of the customer have been accurately determined, the
proposer is able to provide the best proposal that is suitable for
the preferences of the customer.
[0094] It should be noted that, in the aforementioned description,
proposal candidate information was presented in the case where the
determination results based on the biological reaction information
and the dialogue content information have matched as positive with
respect to one question; however, the present disclosure is not
particularly restricted to this example. For example, various
alterations are possible such as proposal candidate information
being presented in the case where the determination results based
on the biological reaction information and the dialogue content
information have all matched as positive with respect to a
plurality of predetermined questions.
[0095] Next, a specific example of the first re-question
information, the second re-question information, and the proposal
candidate information presented as a result of the aforementioned
proposal candidate presentation processing will be described with
the case where the proposer proposes a trip plan for the customer
in a travel agency as a consultant as an example. FIG. 3 is a
drawing depicting an example of summary information created from
the biological reaction information and the dialogue content
information.
[0096] The summary information depicted in FIG. 3 indicates an
example of a display screen displayed on the presentation unit 18,
and the proposer engages in a dialogue with the customer while
looking at this display screen. In the summary information depicted
in FIG. 3, the horizontal axis indicates time and the vertical axis
indicates measurement values for biological data (for example,
heartbeat fluctuation values in arbitrary units). Furthermore, the
solid polygonal line represents changes in the biological data, the
dashed line is a threshold value at which it is determined that the
biological data constitutes a positive reaction if equal to or
greater than that value, and summaries of dialogue content at times
at which the biological data changes are superimposed and
displayed.
[0097] First, as an initial question, for example, the question
generation unit 15 extracts question information with which "Rome"
is proposed, and the presentation unit 18 displays "How about
Rome?" Q1 as the initial question. In accordance with this display,
the proposer inquires "How about Rome'?". At such time, in the case
where the customer has responded with "I am interested", the
customer response "I am interested" A1 is displayed superimposed on
the biological data from at this time. The measurement value for
the biological data from at this time is less than the threshold
value indicating a positive reaction.
[0098] In this case, the countermeasure determination unit 13
judges that the determination based on the biological reaction
information is a negative reaction and the determination based on
the dialogue content information is a positive reaction.
Furthermore, the number of times that the determination results do
not match is 1, and therefore the question generation unit 15
extracts question information proposing "Naples", for example, as
first re-question information, from among question information
having associated therewith the attribute information "city name"
indicating the same perspective as the perspective of the question
regarding "Rome". The presentation unit 18 displays "How about
Naples?" Q2 as the first re-question information.
[0099] Next, when the proposer inquires "How about Naples?" and the
customer responds with "I am not interested", the customer response
"I am not interested" A2 is displayed superimposed on the
biological data from at this time. The measurement value for the
biological data from at this time is equal to or greater than the
threshold value indicating a positive reaction.
[0100] In this case, the countermeasure determination unit 13
judges that the determination based on the biological reaction
information is a positive reaction and the determination based on
the dialogue content information is a negative reaction.
Furthermore, the number of times that the determination results
have not matched is 2, and therefore the question generation unit
15 extracts question information inquiring about "Venice", for
example, as first re-question information, from among question
information having associated therewith the attribute information
"city name" indicating the same perspective as the perspective of
the question regarding "Naples". The presentation unit 18 displays
"How about Venice?" Q3 as the first re-question information.
[0101] Next, when the proposer inquires "How about Venice?" and the
customer responds with "I am interested", the customer response "I
am interested" A3 is displayed superimposed on the biological data
from at this time. The measurement value for the biological data
from at this time is less than the threshold value indicating a
positive reaction.
[0102] In this case, the countermeasure determination unit 13
judges that the determination based on the biological reaction
information is a negative reaction and the determination based on
the dialogue content information is a positive reaction.
Furthermore, the number of times that the determination results
have not matched is 3, and therefore the question generation unit
15 extracts question information inquiring about "French cuisine",
for example, as second re-question information, from among question
information having associated therewith the attribute information
"dining", for example, indicating a different perspective from the
perspective of the question regarding "Venice". The presentation
unit 18 displays "Do you like French cuisine?" Q4 as the second
re-question information.
[0103] Next, when the proposer inquires "Do you like French
cuisine?" and the customer responds with "No, I do not", the
customer response "No, I do not" A4 is displayed superimposed on
the biological data from at this time. The measurement value for
the biological data from at this time is less than the threshold
value indicating a positive reaction.
[0104] In this case, the countermeasure determination unit 13
judges that the determination based on the biological reaction
information is a negative reaction and the determination based on
the dialogue content information is a negative reaction.
Consequently, the question generation unit 15 extracts question
information inquiring about "opera", for example, as second
re-question information, from among question information having
associated therewith the attribute information "music", for
example, indicating a different perspective from the perspective of
the question regarding "French cuisine". The presentation unit 18
displays "Do you like opera?" Q5 as the second re-question
information.
[0105] Next, when the proposer inquires "Do you like opera?" and
the customer responds with "Yes, I do", the customer response "Yes,
I do" A5 is displayed superimposed on the biological data from at
this time. The measurement value for the biological data from at
this time is equal to or greater than the threshold value
indicating a positive reaction.
[0106] In this case, the countermeasure determination unit 13
judges that the determination based on the biological reaction
information is a positive reaction and the determination based on
the dialogue content information is a positive reaction.
Consequently, the proposal candidate generation unit 17 extracts
proposal candidate information that has been set with respect to
the question regarding "opera" asked to the customer by the
proposer, for example, proposal candidate information proposing a
"Milan opera tour" and a "Paris opera tour", from the proposal
candidate storage unit 16. The presentation unit 18 displays "How
about a Milan opera tour or a Paris opera tour?" P1 proposing a
"Milan opera tour" and a "Paris opera tour", as proposal candidate
information.
[0107] Lastly, the proposer confirms the proposal candidate
information P1 proposing a "Milan opera tour" and a "Paris opera
tour", and, in the case of having selected the "Milan opera tour"
based on his or her own judgment, is able to make the proposal "How
about a Milan opera tour?".
[0108] As mentioned above, in the present embodiment, in consulting
work and concierge work in hotels and the like in which products
such as trips are proposed and sold to a customer by a proposer, in
the case where the reaction of the customer based on the biological
reaction information and the reaction of the customer based on the
dialogue content information are both positive reactions, it is
possible for an item that is liked by the customer to be reliably
determined from the response of the customer regarding a question
asked to the customer by the proposer. In addition, by generating
proposal candidate information based on this response of the
customer, proposal candidate information including a proposal that
is liked by the customer can be appropriately presented to the
proposer.
[0109] Furthermore, the proposer is able to carry out first
re-question having the same perspective using first re-question
information, even in the case where the reaction of the customer
based on the biological reaction information and the reaction of
the customer based on the dialogue content information do not match
and an item liked by the customer cannot be accurately determined
from the response of the customer regarding a question asked to the
customer by the proposer. Thus, in the case where the reaction of
the customer based on the biological reaction information and the
reaction of the customer based on the dialogue content information
regarding this first re-question are both positive reactions, an
item liked by the customer can be accurately determined from the
response of the customer regarding the first re-question having the
same perspective, and proposal candidate information including a
proposal that is liked by the customer can be appropriately
presented to the proposer.
[0110] Furthermore, second re-question information representing
second re-question having a different perspective from the
perspective of the question included in the dialogue content is
generated when the case where the reaction of the customer based on
the biological reaction information and the reaction of the
customer based on the dialogue content information do not match has
been repeated a predetermined number of times with respect to
questions represented by the first re-question information. Thus,
second re-question information having a different perspective from
that of the questions asked to the customer by the proposer can be
presented to the proposer, and an item liked by the customer can be
accurately determined from the responses of the customer regarding
the second re-question of the different perspective, in the case
where a state has continued in which an item liked by the customer
cannot be accurately determined from responses of the customer
regarding questions asked to the customer by the proposer.
[0111] In addition, second re-question information representing
second re-question having a different perspective from that of the
question included in the dialogue content is generated in the case
where the reaction of the customer based on the biological reaction
information is a negative reaction and the reaction of the customer
based on the dialogue content information is a negative reaction.
Thus, the proposer is able to carry out second re-question having a
different perspective using the second re-question information,
even in the case where an item liked by the customer cannot be
accurately determined from responses of the customer regarding
questions asked to the customer by the proposer.
[0112] Consequently, an item liked by the customer can be
accurately determined from the response of the customer regarding
the second re-question having a different perspective, and proposal
candidate information including a proposal that is liked by the
customer can be appropriately presented to the proposer, in the
case where the reaction of the customer based on the biological
reaction information and the reaction of the customer based on the
dialogue content information regarding this second re-question are
both positive reactions.
[0113] As a result, proposal candidate information including a
proposal that corresponds to the preferences of the customer can be
presented to the proposer even in the case where there is a
difference between a reaction determined from a response of the
customer regarding a question and a reaction determined from
biological data of the customer regarding the question.
[0114] Hereinabove, a proposal candidate presentation device
according to an aspect of the present disclosure has been described
on the basis of the aforementioned embodiment; however, the present
disclosure is not restricted to the aforementioned embodiment.
Modes in which various modifications conceived by a person skilled
in the art have been implemented in the present embodiment, and
modes constructed by combining the constituent elements in
different embodiments may also be included within the scope of the
present disclosure provided they do not depart from the purpose of
the present disclosure.
[0115] With a proposal candidate presentation device, a proposal
candidate presentation method, and a recording medium having
recorded thereon a proposal candidate presentation program
according to the present disclosure, when a proposer carries out
consulting work and concierge work with respect to a customer
face-to-face or via the Internet in various facilities, proposal
candidate information including a proposal that corresponds to the
preferences of the customer can be presented to the proposer even
in the case where there is a difference between a reaction
determined from a response of the customer regarding a question and
a reaction determined from biological data of the customer
regarding the question. Consequently, the present disclosure is
useful as a proposal candidate presentation device, a proposal
candidate presentation method, and a recording medium having
recorded thereon a proposal candidate presentation program which
present proposal candidate information including at least one
proposal for a customer on the basis of dialogue content including
a question asked to the customer by a proposer and a response of
the customer regarding the question.
* * * * *